Health monitoring is crucial in hospitals and rehabilitation centers. Challenges can affect the reliability and accuracy of health data. Human error, patient compliance concerns, time, money, technology, and environmental factors might cause these issues. In order to improve patient care, healthcare providers must address these challenges. We propose a non-intrusive smart sensing system that uses a SensFloor smart carpet and an inertial measurement unit (IMU) wearable sensor on the user’s back to monitor position and gait characteristics. Furthermore, we implemented machine learning (ML) algorithms to analyze the data collected from the SensFloor and IMU sensors. The system generates real-time data that are stored in the cloud and are accessible to physical therapists and patients. Additionally, the system’s real-time dashboards provide a comprehensive analysis of the user’s gait and balance, enabling personalized training plans with tailored exercises and better rehabilitation outcomes. Using non-invasive smart sensing technology, our proposed solution enables healthcare facilities to monitor patients’ health and enhance their physical rehabilitation plans.

No abstract

Bone marrow edema (BME) is the term given to the abnormal fluid signal seen within the bone marrow on magnetic resonance imaging (MRI). It usually indicates the presence of underlying pathology and is associated with a myriad of conditions/causes. However, it can be misleading, as in some cases, it may be associated with normal changes in the bone, especially during the growth period of childhood, and objective methods for assessment are lacking. In this work, learning models for BME detection were developed. Transfer learning was used to overcome the size limitations of the dataset, and two different regions of interest (ROI) were defined and compared to evaluate their impact on the performance of the model: bone segmention and intensity mask. The best model was obtained for the high intensity masking technique, which achieved a balanced accuracy of 0.792 ± 0.034. This study represents a comparison of different models and data regularization techniques for BME detection and showed promising results, even in the most difficult range of ages: children and adolescents. The application of machine learning methods will help to decrease the dependence on the clinicians, providing an initial stratification of the patients based on the probability of edema presence and supporting their decisions on the diagnosis.